Created
February 14, 2013 19:18
-
-
Save mlconnor/4955479 to your computer and use it in GitHub Desktop.
JavaScript to parse a CSV string and create JSON objects based on the column headers
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
function csvToJson(str) { | |
var data = [], i = 0, k = 0, header = []; | |
var csvLines = CSVToArray(str); | |
for ( i = 0; i < csvLines.length; i++ ) { | |
var line = csvLines[i]; | |
if ( i == 0 ) { | |
header = csvLines[i]; | |
} else { | |
var obj = {}; | |
for ( k = 0; k < header.length; k++ ) { | |
if ( k < csvLines[i].length ) { | |
obj[header[k]] = csvLines[i][k]; | |
} | |
} | |
data.push(obj); | |
} | |
} | |
return data; | |
} | |
// this code was found here http://www.bennadel.com/blog/1504-Ask-Ben-Parsing-CSV-Strings-With-Javascript-Exec-Regular-Expression-Command.htm | |
// This will parse a delimited string into an array of | |
// arrays. The default delimiter is the comma, but this | |
// can be overriden in the second argument. | |
function CSVToArray( strData, strDelimiter ){ | |
// Check to see if the delimiter is defined. If not, | |
// then default to comma. | |
strDelimiter = (strDelimiter || ","); | |
// Create a regular expression to parse the CSV values. | |
var objPattern = new RegExp( | |
( | |
// Delimiters. | |
"(\\" + strDelimiter + "|\\r?\\n|\\r|^)" + | |
// Quoted fields. | |
"(?:\"([^\"]*(?:\"\"[^\"]*)*)\"|" + | |
// Standard fields. | |
"([^\"\\" + strDelimiter + "\\r\\n]*))" | |
), | |
"gi" | |
); | |
// Create an array to hold our data. Give the array | |
// a default empty first row. | |
var arrData = [[]]; | |
// Create an array to hold our individual pattern | |
// matching groups. | |
var arrMatches = null; | |
// Keep looping over the regular expression matches | |
// until we can no longer find a match. | |
while (arrMatches = objPattern.exec( strData )){ | |
// Get the delimiter that was found. | |
var strMatchedDelimiter = arrMatches[ 1 ]; | |
// Check to see if the given delimiter has a length | |
// (is not the start of string) and if it matches | |
// field delimiter. If id does not, then we know | |
// that this delimiter is a row delimiter. | |
if ( | |
strMatchedDelimiter.length && | |
(strMatchedDelimiter != strDelimiter) | |
){ | |
// Since we have reached a new row of data, | |
// add an empty row to our data array. | |
arrData.push( [] ); | |
} | |
// Now that we have our delimiter out of the way, | |
// let's check to see which kind of value we | |
// captured (quoted or unquoted). | |
if (arrMatches[ 2 ]){ | |
// We found a quoted value. When we capture | |
// this value, unescape any double quotes. | |
var strMatchedValue = arrMatches[ 2 ].replace( | |
new RegExp( "\"\"", "g" ), | |
"\"" | |
); | |
} else { | |
// We found a non-quoted value. | |
var strMatchedValue = arrMatches[ 3 ]; | |
} | |
// Now that we have our value string, let's add | |
// it to the data array. | |
arrData[ arrData.length - 1 ].push( strMatchedValue ); | |
} | |
// Return the parsed data. | |
return( arrData ); | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment